"An on-line handwritten character recognition technique based on a template matching distance is proposed. In this method, the pen-direction features are quantized using the 8-level Freeman chain coding scheme and the dominant points of the stroke are identified using the first difference of the chain code. The distance between two symbols results from the difference of the respective chain codes of the variable speed normalization of dominant points weighted by the local length proportions of the strokes. The proposed technique was tested on two datasets and showed a recognition rate of 92 % in the top 1 choice."

Full text: